Information processing method and device, server and user equipment

Abstract

The present invention provides an information processing method and apparatus, a server, and a user device. The method comprises: detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user; in response to a sample acquisition request initiated by the target user, invoking the parameter sampling algorithm to generate a test sample; determining a simulation result of the test sample based on a preset objective function; and outputting the simulation result of the test sample to the target user. The present invention improves the efficiency of parameter optimization.

Description

Technical Field

[0001] The present application relates to the technical field of electronic equipment, and in particular to an information processing method and apparatus, a server, and user equipment. Background Art

[0002] Black-box algorithms are designed to solve complex problems that cannot be modeled using explicit mathematical formulas. Their mathematical models are typically unknown. Input data is fed into the algorithm's objective function, and the corresponding output data is calculated. During the actual computational process, the specific objective function is unknown. Due to their wide range of services and selectivity, black-box algorithms are applicable to a wide range of fields, including e-commerce, finance, and electricity.

[0003] In existing technology, developers can implement black-box optimization based on the AutoML (Automated Machine Learning) framework. The main process of black-box optimization is to continuously generate new samples for the parameters to be optimized using a parameter sampling algorithm. The black-box objective function is then used to evaluate the effectiveness of the samples to obtain simulation results. After that, the parameter sampling algorithm is continuously used to generate new samples and perform simulation evaluations to quickly generate a target sample that is close to the simulation result and meets predetermined conditions. This target sample and the corresponding simulation result are the optimization results of this black-box optimization.

[0004] However, after being developed by developers, existing black-box optimization processes are mainly performed locally, resulting in low black-box optimization efficiency. Summary of the Invention

[0005] In view of this, embodiments of the present application provide an information processing method and apparatus, a server, and a user device to solve the technical problem in the prior art of low black box optimization efficiency due to local execution of the black box optimization process.

[0006] In a first aspect, an embodiment of the present application provides an information processing method, including:

[0007] Detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user;

[0008] In response to a sample acquisition request initiated by the target user, calling the parameter sampling algorithm to generate a test sample;

[0009] Determining a simulation result of the test sample based on a preset objective function;

[0010] Outputting simulation results of the test sample to the target user.

[0011] In a second aspect, an embodiment of the present application provides an information processing method, including:

[0012] Receive a parameter optimization request initiated by a target user for the pending parameters of a target resource;

[0013] Determining a parameter sampling algorithm that matches the processing goal of the target resource;

[0014] In response to a sample acquisition request initiated by the target user for the parameter to be processed, calling the parameter sampling algorithm to generate a test sample of the parameter to be processed;

[0015] Determining a simulation result of the test sample based on a preset objective function;

[0016] Outputting simulation results corresponding to the test samples of the parameters to be processed to the target user, so that the target user can process the target resource according to the test samples.

[0017] In a third aspect, an embodiment of the present application provides an information processing method, including:

[0018] receiving a parameter optimization request for a browsing parameter corresponding to a browsing operation initiated by the target user;

[0019] Determining a parameter sampling algorithm that matches the browsing goal of the target user;

[0020] In response to a sample acquisition request initiated by the target user for the browsing parameter, calling the parameter sampling algorithm to generate a test sample of the browsing parameter;

[0021] Determining a simulation result of the test sample based on a preset objective function;

[0022] The simulation result corresponding to the test sample of the browsing parameter is output to the target user, so that the target user can configure the browsing parameter according to the test sample.

[0023] In a fourth aspect, an embodiment of the present application provides an information processing method, including:

[0024] Detect parameter optimization requests initiated by target users for parameter sampling algorithms;

[0025] Sending the parameter optimization request to a server, so that the server can determine a parameter sampling algorithm that matches the target user;

[0026] Sending the sample acquisition request initiated by the target user to the server, so that the server responds to the sample acquisition request and calls the parameter sampling algorithm to generate a test sample;

[0027] Determining a simulation result of the test sample based on a preset objective function;

[0028] Outputting simulation results of the test sample to the target user.

[0029] In a fifth aspect, an embodiment of the present application provides an information processing method, including:

[0030] In response to a request to call an information processing interface, determining a processing resource corresponding to the information processing interface;

[0031] The following steps are performed using the processing resources corresponding to the information processing interface:

[0032] Detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user;

[0033] In response to a sample acquisition request initiated by the target user, calling the parameter sampling algorithm to generate a test sample;

[0034] Determining a simulation result of the test sample based on a preset objective function;

[0035] Outputting simulation results of the test sample to the target user.

[0036] In a sixth aspect, an embodiment of the present application provides an information processing device, including:

[0037] A request detection module is used to detect parameter optimization requests initiated by a target user and determine a parameter sampling algorithm that matches the target user;

[0038] A first response module, configured to respond to a sample acquisition request initiated by the target user and call the parameter sampling algorithm to generate a test sample;

[0039] A first simulation module, configured to determine a simulation result of the test sample based on a preset objective function;

[0040] The first output module is used to output the simulation result of the test sample to the target user.

[0041] In a seventh aspect, an embodiment of the present application provides an information processing device, including:

[0042] The request initiation module is used to detect the parameter optimization request initiated by the target user for the parameter sampling algorithm;

[0043] A first sending module is configured to send a parameter optimization request provided by a target user to a server, so that the server can determine a parameter sampling algorithm that matches the target user;

[0044] A second sending module is configured to send the sample acquisition request initiated by the target user to the server, so that the server responds to the sample acquisition request and calls the parameter sampling algorithm to generate a test sample;

[0045] A second simulation module, configured to determine a simulation result of the test sample based on a preset objective function;

[0046] The second output module is used to output the simulation result of the test sample to the target user.

[0047] In an eighth aspect, an embodiment of the present application provides a server, comprising: a storage component and a processing component; the storage component is used to store one or more computer instructions; the one or more computer instructions are called by the processing component;

[0048] The processing component is used to:

[0049] Detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user; in response to a sample acquisition request initiated by the target user, calling the parameter sampling algorithm to generate a test sample; determining a simulation result of the test sample based on a preset objective function; and outputting the simulation result of the test sample to the target user.

[0050] In a ninth aspect, an embodiment of the present application provides a user terminal, comprising: a storage component and a processing component; the storage component is used to store one or more computer instructions; the one or more computer instructions are called by the processing component;

[0051] The processing component is used to:

[0052] Detecting a parameter optimization request initiated by a target user for a parameter sampling algorithm; sending the parameter optimization request provided by the target user to a server, so that the server can determine a parameter sampling algorithm that matches the target user; sending a sample acquisition request initiated by the target user to the server, so that the server can respond to the sample acquisition request and call the parameter sampling algorithm to generate a test sample; determining a simulation result of the test sample based on a preset objective function; and outputting the simulation result of the test sample to the target user.

[0053] An embodiment of the present application can receive a parameter optimization request initiated by a target user and determine a parameter sampling algorithm that matches the target user. Afterwards, in response to a sample acquisition request initiated by the target user, the parameter sampling algorithm can be called to generate a test sample. The test sample can be used to determine the simulation result in the calculation method of the objective function, thereby outputting the simulation result of the test sample for the target user. Through interaction with the target user, a cloud service for parameter optimization is implemented to achieve rapid parameter optimization in the cloud and improve the efficiency of parameter optimization. In addition, by obtaining the user's parameter optimization request and sample acquisition request, the user's service needs are obtained, and by effectively responding to and providing feedback on the user's service needs, black box services are effectively provided to the user, the extended application of black box services is achieved, and the utilization efficiency of the black box algorithm is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0055] Figure 1 A flowchart of an embodiment of an information processing method provided in an embodiment of the present application;

[0056] Figure 2 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0057] Figure 3 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0058] Figure 4 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0059] Figure 5 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0060] Figure 6 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0061] Figure 7 An example diagram of an application of an information processing method provided in an embodiment of the present application;

[0062] Figure 8 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0063] Figure 9 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0064] Figure 10 A schematic structural diagram of an embodiment of an information processing device provided in an embodiment of the present application;

[0065] Figure 11 A schematic diagram of the structure of an embodiment of a server provided in an embodiment of the present application;

[0066] Figure 12 A schematic structural diagram of another embodiment of an information processing device provided in an embodiment of the present application;

[0067] Figure 13 A schematic structural diagram of an embodiment of a user equipment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0068] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0069] The terms used in the examples of this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms "a," "the," and "the" used in the examples of this application and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two, but does not exclude the inclusion of at least one.

[0070] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0071] As used herein, the words “if” and “if” may be interpreted as “at the time of” or “when” or “in response to determining” or “in response to identifying,” depending on the context. Similarly, the phrases “if it is determined” or “if (stated condition or event) is identified” may be interpreted as “when it is determined” or “in response to determining” or “when identifying (stated condition or event)” or “in response to identifying (stated condition or event),” depending on the context.

[0072] It should also be noted that the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a product or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such product or system. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the product or system comprising the element.

[0073] The technical solution of the embodiment of the present application can be applied to the parameter optimization process. By providing external black box services, multi-user application of black box optimization can be realized, the scope of application of black box optimization can be expanded, and the utilization efficiency of black box optimization can be improved.

[0074] In the prior art, after developers develop black box algorithms based on AutoML (Automated Aachine Learning, automated learning framework), they can use the added black box optimization service. The main process of black box optimization is to use the black box algorithm to continuously generate new samples, and use a simulation function that simulates the actual calculation effect of the user, that is, the objective function to simulate the use effect of the generated new samples to obtain the simulation result of the sample. By continuously generating new samples and continuously simulating the effects of the newly generated samples, the sample with the highest use effect is selected from the many samples obtained as the global target solution. However, the existing black box algorithms, or black box optimization strategies are mostly used internally by developers, resulting in a narrow application scope of black box optimization and low utilization of black box algorithms.

[0075] In an embodiment of the present application, a parameter optimization request initiated by a target user can be detected, and a parameter sampling algorithm that matches the target user can be determined. By providing an external black box service, the target user can use the black box algorithm for parameter optimization at any time. After the parameter sampling algorithm is called to generate a test sample in response to the sample acquisition request initiated by the target user, the simulation result of the test sample can be determined based on the preset objective function, and the test sample can be automatically generated for the target user, and the simulation calculation of the test sample can be completed. The simulation result is usually an estimated result of the use effect of the test sample, so as to accurately evaluate the test sample. After the simulation result of the test sample is output to the target user, it can be viewed by the target user and determine whether the test sample is available, thereby realizing the effect test of the test sample. Through interaction with the target user, a cloud service for parameter optimization is realized to achieve rapid parameter optimization in the cloud and improve the efficiency of parameter optimization. In addition, by effectively providing black box services to users, the extended application of black box services is realized and the utilization efficiency of black box algorithms is improved.

[0076] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0077] like Figure 1 FIG. 1 is a flowchart of an embodiment of an information processing method provided by an embodiment of the present application. The method may include the following steps:

[0078] 101: Detect the parameter optimization request initiated by the target user and determine a parameter sampling algorithm that matches the target user.

[0079] The information processing method provided in the embodiments of the present application can be applied to a server side. The server side is relative to the client side, and the server side and the client side correspond to the C / S (Client-Server) architecture. In practical applications, the server side can be, for example, a computer, an ordinary server, a cloud server, a super personal computer, a laptop computer, a tablet computer, etc. The client side can be configured on a user device, and the client side can be, for example, a mobile phone, a tablet computer, a computer, a virtual reality device, an augmented reality device, a wearable device, etc. The embodiments of the present application do not impose too many restrictions on the specific types of the server side and the client side.

[0080] Optionally, the server can be configured with multiple parameter sampling algorithms. Different parameter sampling algorithms operate on different principles, but produce the same results, and can all be used to generate test samples. A general parameter sampling algorithm can be used to generate samples of parameters to be optimized, and then simulate the effects of the samples using a preset objective function to estimate the effects of the samples and obtain simulation results for the samples. By continuously generating samples and obtaining simulation results for the samples, the target samples with the highest simulation result evaluation can be selected and output as the parameter optimization result, completing the parameter optimization.

[0081] The target user can send a parameter optimization request to the server through the user terminal. The server can receive the parameter optimization request sent by the target user's user terminal. The parameter optimization request can be generated by the target user based on the parameters to be optimized. Taking content recommendation in the e-commerce field as an example, when the target user browses an e-commerce website, the website can push content that the target user is interested in. However, since there are many types of content, different types of content contribute differently to click-through rates. Therefore, the proportion of recommended content of each type can be used as a parameter to be optimized.

[0082] The server can be configured with multiple candidate sampling algorithms. The target user can specify a parameter sampling algorithm from among multiple black-box algorithms in the parameter optimization request. In this case, the parameter optimization request can include the algorithm identification information of the parameter sampling algorithm. The algorithm identification information can be, for example, the algorithm name.

[0083] In addition, the parameter optimization request may also include parameter information such as sample type, value range, quantity, etc. corresponding to the samples of the parameters to be optimized. In some optional embodiments, the parameter sampling algorithm can simultaneously generate multiple samples of the parameters to be optimized, so as to evaluate multiple samples at the same time and improve the efficiency of parameter optimization. In order to identify the parameter optimization requests of different users, the parameter optimization request may also include a test identifier set for the target user's parameter optimization test to distinguish it from the optimization process of different parameters. The target user can also use user information such as username and password to log in to the server to obtain permission to use the parameter optimization service and realize effective management of users.

[0084] Optionally, in actual applications, when the server receives a parameter optimization request, it can store parameter information, user information, test identification and other information in the parameter optimization request to accurately track the process and results of the parameter optimization service and improve information processing efficiency.

[0085] 102: In response to the sample acquisition request initiated by the target user, a parameter sampling algorithm is called to generate a test sample.

[0086] After the server determines the parameter sampling algorithm that matches the target user, it can provide the target user with a startup prompt to initiate parameter optimization. After the target user sends a parameter optimization request, the server can also provide a startup prompt corresponding to the parameter optimization. When the target user confirms the launch of the black-box algorithm, they can send a sample acquisition request to the server. The server can receive the sample acquisition request sent by the target user, respond to it, and invoke the parameter sampling algorithm to generate test samples.

[0087] The test sample may be a parameter value set for the parameter to be optimized, specifically a candidate solution generated by the parameter sampling algorithm for the parameter to be optimized. When the candidate solution meets the optimization conditions, it constitutes the final optimization result of the parameter to be optimized.

[0088] 103: Determine the simulation result of the test sample based on the preset objective function.

[0089] The objective function can simulate the use effect or use result of the test sample to obtain the simulation result. The objective function can be determined by the optimization target of the parameter to be optimized. For example, in the content recommendation scenario, the parameter to be optimized can be the parameter corresponding to the recommended content. The test sample is the recommended content displayed to the browsing user based on the parameter to be optimized. The higher the probability of the user clicking on the recommended content, the more effective the content recommendation is. Therefore, the click-through rate prediction model can be used as the objective function to predict the click-through rate of the browsing user on the recommended content. The predicted click-through rate is the simulation result of the test sample.

[0090] 104: Output the simulation results of the test samples to the target user.

[0091] Optionally, outputting the simulation result of the test sample to the target user may include: sending the simulation result of the test sample to a user terminal of the target user, so that the user terminal displays the output result of the test sample.

[0092] As a possible implementation method, when the server sends the simulation result of the test sample to the user terminal of the target user, it can be sent to the user terminal of the target user in the form of a web page, instant messaging message, short message, etc.

[0093] In an embodiment of the present application, the parameter optimization request initiated by the target user can be detected, and the parameter sampling algorithm that matches the target user can be determined. By providing an external black box service, the target user can use the black box algorithm to optimize the parameters at any time. After the parameter sampling algorithm is called to generate a test sample in response to the sample acquisition request initiated by the target user, the simulation result of the test sample can be determined based on the preset objective function, and the test sample can be automatically generated for the target user, and the simulation calculation of the test sample can be completed. Through interaction with the target user, a cloud service for parameter optimization is realized to achieve rapid parameter optimization in the cloud and improve the efficiency of parameter optimization. In addition, by obtaining the user's black box service request parameter optimization request and sample acquisition request, the user's service needs can be obtained, and by effectively responding to and providing feedback on the user's service needs, the user can be effectively provided with a black box service, the extended application of the black box service can be realized, and the utilization efficiency of the black box algorithm can be improved.

[0094] In certain embodiments, the simulation result of the test sample is typically an evaluation result obtained by evaluating the use effect of the test sample based on the objective function. The use effect of the test sample can be accurately evaluated through the simulation result. After the simulation result of the test sample is output to the target user, the target user views the simulation result of the test sample to directly determine whether the test sample meets the use requirements through the simulation result, thereby achieving accurate prompting of the use effect of the test sample. For example, in the aforementioned content recommendation example, when the click-through rate calculation model is used as the objective function, the higher the click-through rate calculated, the more effective the recommended content. When the click-through rate reaches the threshold set by the target user, the target user can confirm that the test sample meets the use conditions. At this time, the test sample can be provided to the recommendation system so that the recommendation system generates recommended content based on the test sample and recommends it to users using the recommendation system.

[0095] In an embodiment of the present application, it can be open to many types of target users such as system developers, scholars, students, system designers, and corporate users to provide parameter optimization services to different types of target users. When effectively providing parameter optimization services to target users, target users can continuously initiate sample acquisition requests, and the server can continuously respond to sample acquisition requests and provide test samples to target users, so that target users can learn the simulation results of each test sample and select target samples that meet their usage conditions. Providing parameter optimization services to different target users realizes the expanded application of parameter optimization services, enables more users to use parameter optimization services, and improves the utilization efficiency of parameter optimization.

[0096] In an embodiment of the present application, the objective function may specifically belong to a black box algorithm and cannot be expressed using a clear mathematical formula. The specific mathematical model of the objective function is usually unknown. In this case, the parameter optimization request may include a black box optimization request.

[0097] As an embodiment, detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user may include:

[0098] Detect the black-box optimization request initiated by the target user and determine the parameter sampling algorithm that matches the target user.

[0099] The technical solutions of the embodiments of the present application can be applied to cloud servers, which may include public clouds and private clouds. Among them, a public cloud can be a cloud that can be used by third-party service users on the cloud, generally used through the network to realize shared resource services, and can provide services for open public networks. A private cloud is built for the sole use of a single customer, and thus provides the most effective control over data, security, and service quality. Therefore, the security of a private cloud is higher than that of a public cloud. For the sake of data security, when a user uses the information processing method configured in the cloud, the processing procedures of the public cloud and the private cloud may be different.

[0100] When using an objective function to simulate test samples, a large amount of user information or data is involved. For private clouds, since private clouds serve individual users and have a high degree of privacy, the simulation process can be completed on the private cloud to reduce processing pressure on the user side. For public clouds, since public clouds serve many users and lack privacy, the simulation process can be completed on the user side to ensure data security.

[0101] In one possible design, the public cloud and the private cloud can be implemented as underlying services based on K8S. K8S (Kubernets, container cluster management system) can be used to automatically deploy, scale and manage containerized applications. A cluster is a group of nodes. A cloud server, whether a public cloud or a private cloud, can be regarded as a service cluster. A service cluster can be composed of multiple nodes. The K8S platform is installed on these nodes to facilitate the use of K8S to manage the nodes in the cluster. The information processing method in the embodiment of the present application can be applied to the K8S platform, and can be specifically configured on the Custom resource controller (CRD, custom resource controller) created in the K8S platform, that is, the CRD in K8S can be used as a processing component to implement the information processing method.

[0102] The technical solution of the embodiment of the present application can be configured based on the underlying K8S service. The functions of each step can be modularized and then configured on the node. Based on the functional modules, an external service interface can be provided. Through the external service interface, data or information interaction with the user end can be achieved, providing parameter optimization services for users. For example, a cloud server can be configured with a gateway, data storage component, black box algorithm component, early stopping component, web (World Wide Web) page, sample collection system, database and other components based on K8S. The technical solution of the embodiment of the present application is completed through the cooperation of these components.

[0103] In some embodiments, the gateway can be a Rest (Representational State Transfer) API (Application Programming Interface) gateway API Server of K8S; the data storage component can be a distributed storage component Etcd (storing cluster status information) of K8S; the black box algorithm component can be a core algorithm component Suggestion Service provided to developers, for example, it can include: random search / grid search / cmaes (maximum likelihood estimation) / pma (Partitioning Around Medoid, partitioning around the center point) or one or more; the early stop component can simulate undesirable parameters of the process through early stopping technology, stop early, reduce resource consumption, and accelerate the progress of the test; the web page is mainly used to output test samples and simulation results of test samples to users, so that users can view them in time; the sample collection system (Metric System) can be used to collect black box test samples in the pod (scheduling unit); the database can be a database such as MySQL, which is used to store test samples and data generated by the simulation process and simulation results.

[0104] When the cloud server is a public cloud, the simulation process of the test sample can be completed on the user side to reduce the possibility of data leakage and improve data security. Figure 2 FIG. 1 is a flowchart of another embodiment of an information processing method provided by an embodiment of the present application. The method may include the following steps:

[0105] 201: Detect the parameter optimization request initiated by the target user and determine a parameter sampling algorithm that matches the target user.

[0106] Some steps in the embodiments of this application are Figure 1 Some of the steps shown are the same and will not be repeated here for the sake of brevity. In an embodiment of the present application, a parameter optimization request can be sent from a user terminal to a server terminal, and the server terminal can provide an interface for external communication, that is, an information processing interface, and receive the parameter optimization request sent by the user terminal through the information processing interface.

[0107] Optionally, when the user terminal initiates a parameter optimization request to the server terminal, the request service information composed of algorithm information, parameter information, user information and / or verification information input on the user terminal can be sent to the server terminal in the form of SDK (Software Development Kit). The information processing interface of the server terminal can receive the parameter optimization request encapsulated in the form of SDK and obtain the parameter sampling algorithm corresponding to the request service information.

[0108] 202: In response to the sample acquisition request initiated by the target user, a parameter sampling algorithm is called to generate a test sample.

[0109] 203: Sending the test sample to the user terminal of the target user, so that the user terminal inputs the test sample into a preset objective function and calculates and obtains a simulation result corresponding to the test sample.

[0110] Sending the test sample to the target user's client, which then completes the simulation of the test sample, can reduce the risk of data leakage and improve data security.

[0111] Optionally, before sending the test sample to the user terminal of the target user, the method may further include: receiving a sample test request sent by the user terminal of the target user, responding to the sample test request, and sending the test sample to the user terminal of the target user.

[0112] In another possible design, a test prompt can be given to the target user. For example, a test prompt information can be generated. The test prompt information can include risk warning information for sample testing on a public cloud, such as reminding the target user in the form of a text message that "whether to perform simulation calculations of test samples on a public cloud, there is a risk of data leakage". At this time, after the user terminal receives the risk warning information, the risk warning information can be output to the target user, so that the target user can view the risk warning information and make corresponding feedback operations on the risk warning information. In some embodiments, the target user can directly perform a confirmation operation on the simulation of the test sample on the user terminal. When the server detects the confirmation operation, it can send the test sample to the user terminal of the target user.

[0113] 204: Receive simulation results corresponding to the test samples sent by the user terminal.

[0114] 205: Output the simulation results of the test samples to the target user.

[0115] Optionally, outputting the simulation result of the test sample for the target user may include: controlling the target user to output the simulation result of the test sample. For example, when the server receives the simulation result of the test sample, it can verify the simulation result. After the verification is successful, it can output the output control information of the simulation result to the user end. The user end can respond to the output control information of the simulation result and output the simulation result.

[0116] In an embodiment of the present application, the parameter optimization request initiated by the target user is detected, and the parameter sampling algorithm that matches the target user can be determined. In response to the sample acquisition request initiated by the target user, the parameter sampling algorithm can be called to generate a test sample. The test sample is thus sent to the user terminal of the target user, so that the user terminal can input the test sample into a preset objective function and calculate the simulation result corresponding to the test sample. The testing work of the test sample is placed on the user terminal, which reduces data transmission and improves interaction efficiency. After receiving the simulation result corresponding to the test sample sent by the user terminal, the simulation result of the test sample can be output to the target user.

[0117] When the cloud server is a private cloud, the simulation process of the test sample can be completed on the user side to ensure data security. Figure 3 FIG. 1 is a flowchart of another embodiment of an information processing method provided by an embodiment of the present application. The method may include the following steps:

[0118] 301: Detect the parameter optimization request initiated by the target user and determine the parameter sampling algorithm that matches the target user.

[0119] Some steps in the embodiments of this application are Figure 1 、 Figure 2 Some of the steps in the illustrated embodiments are the same and will not be repeated here for the sake of brevity. In the embodiments of the present application, a parameter optimization request may be sent from a user terminal to a server terminal, and the server terminal may provide an interface for external communication, i.e., an information processing interface, and receive the parameter optimization request sent by the user terminal through the information processing interface.

[0120] Optionally, when the user side initiates a parameter optimization request to the server side, the request service information composed of information such as algorithm information, parameter information, user information and / or verification information input on the user side can be sent to the server side in the form of a declarative API (Application Programming Interface). Declarative means that the user side submits an API object that defines the request service information to declare the specific content and type of the desired request service information. The declarative API can contribute to the project orchestration capabilities of the K8S service, so that parameter optimization requests can interact between the user side and the server side in a certain object format to achieve accurate transmission of information.

[0121] When the server receives a parameter optimization request, it can parse it according to the information type and amount defined in the parameter optimization request to obtain relevant information in the parameter optimization request, thereby determining a parameter sampling algorithm that matches the target user.

[0122] As can be seen from the description of the aforementioned embodiments, the black-box algorithm component can actually include multiple classic algorithms, one of which is the parameter sampling algorithm. In some embodiments, the parameter sampling algorithm can be directly specified by the target user. In other words, in this case, the parameter optimization request can include the algorithm identification information of the parameter sampling algorithm. In other embodiments, the parameter sampling algorithm can be determined by the server based on the parameter information provided by the target user, so as to select a more suitable black-box algorithm for the parameter information, thereby improving the applicability of the parameter sampling algorithm to the current parameter optimization requirements.

[0123] 302: In response to the sample acquisition request initiated by the target user, a parameter sampling algorithm is called to generate a test sample.

[0124] 303: Input the test sample into a preset objective function and calculate the simulation result of the test sample.

[0125] Optionally, inputting the test sample into a preset objective function and calculating a simulation result of the test sample may include: determining a scheduling execution unit (Pod) of the objective function, inputting the test sample into the objective function in the scheduling execution unit, and having the scheduling execution unit calculate the simulation result of the test sample. The scheduling execution unit is a computing module provided by the K8S service.

[0126] 304: Output the simulation results of the test samples to the target user.

[0127] In an embodiment of the present application, when the server detects the parameter optimization request initiated by the target user and determines the parameter sampling algorithm that matches the target user, it can respond to the sample acquisition request initiated by the target user and call the parameter sampling algorithm to generate a test sample. The test sample is input into the preset objective function, the simulation result of the test sample is calculated, and the simulation result of the test sample is output to the target user. Completing the simulation process of the test sample on the server can reduce the processing pressure on the user side. In addition, since the computing efficiency of the server is generally higher than that of the user side, the processing efficiency of the test sample can be improved. By providing an external black box service, the target user can use the black box algorithm for parameter optimization at any time, thereby improving the utilization efficiency of the black box algorithm.

[0128] Optionally, when the server is a cloud server, the cloud server can be integrated by multiple nodes, and the parameter sampling algorithm can be run by one of the nodes. As an embodiment, after detecting the parameter optimization request initiated by the target user and determining the parameter sampling algorithm that matches the target user, it also includes:

[0129] Determine the target node for starting the parameter sampling algorithm;

[0130] In response to a sample acquisition request initiated by a target user, calling a parameter sampling algorithm to generate a test sample includes:

[0131] In response to the sample acquisition request, sending the sample acquisition request to a target node for starting a parameter sampling algorithm;

[0132] Get the test samples generated by the parameter sampling algorithm through the target node.

[0133] Optionally, the cloud server is based on a large-scale server cluster and can be composed of multiple computing nodes. The target node for starting the parameter sampling algorithm can be determined by node query. Optionally, determining the target node for starting the parameter sampling algorithm can include: querying the target node for starting the black box algorithm from multiple nodes through a reverse proxy. As a possible implementation method, the operating status of the black box algorithm in each node can be detected. The black box algorithm can be configured separately in different nodes, and one or more black box algorithms can be configured in any node.

[0134] In a K8S-based cloud server, the parameter sampling algorithm can be run on a node in the cloud server, and the client can actually obtain test samples from the target node running the parameter sampling algorithm. Usually, the communication between the client and the target node can be achieved through a router.

[0135] As a possible implementation method, inputting the test sample into a preset objective function and calculating the simulation result of the test sample may include:

[0136] Establish a simulation module for the target function;

[0137] The test sample is input into the simulation module and the simulation result of the test sample is obtained by calculation.

[0138] The target function relies on the support of the computing module during operation. Therefore, to enable the target function to simulate the test samples normally, a simulation module is established for the target function. In the Kubernetes service, the simulation module can be a Pod.

[0139] The server can simultaneously receive parameter optimization requests sent by multiple user terminals, thereby serving multiple user terminals at the same time, or a user terminal can establish different parameter optimization requests for different optimization requirements. The server can also simultaneously receive multiple parameter optimization requests sent by a user terminal. Therefore, in order to distinguish different black box optimization processes, the target user can send a simulation test identifier to the server when initiating a parameter optimization request to distinguish different black box services.

[0140] Therefore, as a possible implementation, the method may further include:

[0141] Receiving a simulation test identifier sent by a target user;

[0142] Based on the simulation test identifier, the simulation results of the test samples are stored for the target user.

[0143] Optionally, receiving the simulation test identifier sent by the target user can specifically be receiving the simulation test identifier sent by the target user when detecting the parameter optimization request initiated by the target user. The simulation test identifier is used to identify the simulation test of the test sample in the parameter optimization request initiated by the target user. For example, when the target user A and the target user B initiate the parameter optimization request at the same time, when the target user A initiates the parameter optimization request, the simulation test identifier a can also be sent to the cloud server, and when the target user B initiates the parameter optimization request, the simulation test identifier b can also be sent to the cloud server. When the target user A initiates a sample acquisition request, the test sample generated for the target user A and the simulation result of the test sample can be identified by the simulation test identifier a. When the target user B initiates a sample acquisition request, the test sample generated for the target user B and the simulation result of the test sample can be identified by the simulation test identifier b to distinguish them from the test sample and simulation result generated for the target user A and identified by the simulation test identifier a.

[0144] In actual applications, when the server provides black box optimization services, it can start the black box optimization process based on the parameter sampling algorithm specified by the user. Figure 4 FIG. 1 is a flowchart of another embodiment of an information processing method provided by an embodiment of the present application. The method may include:

[0145] 401: Receive parameter optimization request initiated by the target user.

[0146] The parameter optimization request includes request service information for the parameter sampling algorithm.

[0147] Optionally, before receiving a parameter optimization request from a target user, the method may further include: sending multiple black-box algorithms to a user terminal of the target user, for the user terminal to output the multiple black-box algorithms for the target user, and selecting a parameter sampling algorithm from the multiple black-box algorithms. The service request information may include information that can be used to identify the black-box algorithm, such as the algorithm name and algorithm identifier.

[0148] 402: When detecting that a storage operation of the service request information exists in the data storage component, a parameter sampling algorithm for the service requested by the target user in the service request information is determined.

[0149] The request service information consists of information such as algorithm information, parameter information, user information, and / or verification information entered by the user. After the server performs operations such as verification on the parameter optimization request, it can store the request service information. In Kubernetes services, etcd (distributed consensus protocol) is typically used to store request service information. Etcd is a distributed storage component developed in Kubernetes that can store network configuration and object status information in the server cluster.

[0150] Optionally, etcd may specifically detect the storage operation of requesting service information. When etcd has a storage action, it may initiate a storage message to the processing component so that the storage component may promptly determine that the data storage component has a storage operation of requesting service information.

[0151] 403: In response to the sample acquisition request initiated by the target user, the parameter sampling algorithm is called to generate a test sample.

[0152] 404: Determine a simulation result of the test sample based on a preset objective function.

[0153] 405: Output the simulation results of the test sample to the target user.

[0154] Some steps in the examples of this application are Figures 1 to 3 Some steps in the illustrated embodiments are the same and will not be described again for the sake of brevity.

[0155] In an embodiment of the present application, the parameter optimization request initiated by the target user may include the request service information of the parameter sampling algorithm specified by the target user. The server can detect the storage behavior of the data storage component. When it is detected that the data storage component has a storage operation of the request service information, the parameter sampling algorithm requested by the target user in the request service information can be determined. By specifying the black box service algorithm by the user, targeted services can be achieved, and the user's controllability of the black box algorithm is enhanced. After determining the parameter sampling algorithm, the parameter sampling algorithm can be called to generate a test sample in response to the sample acquisition request initiated by the target user. Based on the preset objective function, the simulation result of the test sample is determined, and the simulation result of the test sample is output to the target user. By providing an external black box service, the target user can select the parameter sampling algorithm for parameter optimization at any time, thereby improving the utilization efficiency of the black box algorithm.

[0156] In actual applications, the service request information may also include verification information, which may include identity verification information, authority verification information, etc. of the target user.

[0157] In one possible design, after receiving the parameter optimization request sent by the target user, the method may further include:

[0158] Based on the verification information in the service request information, the parameter optimization request of the target user is verified to obtain the verification result;

[0159] If the verification result is successful, the request service information is stored in the data storage component.

[0160] Optionally, the verification information may include identity verification information and permission verification information of the target user. Based on the verification information in the service request information, verifying the parameter optimization request of the target user, and obtaining the verification result may include verifying the user identity of the target user based on the identity verification information in the service request information to obtain the identity verification result.

[0161] The target user's usage authority is verified based on the authority verification information in the service request information to obtain the authority verification result.

[0162] The verification result is determined by combining the identity verification result and the permission verification result.

[0163] Further, optionally, comprehensively considering the identity verification result and the authority verification result, determining the verification result may include: if the identity verification result is verification success and the authority verification result is verification success, determining the verification result is verification success; if the identity verification result is verification failure or the authority verification result is verification failure, determining the verification result is verification failure.

[0164] In some embodiments, if the verification result is a verification failure, a prompt message of the verification failure is fed back to the user terminal of the target user, so that the user terminal can output a prompt message of the verification failure to the target user, remind the user of the reason for the failure of the identity information or permission information, and modify the information or permission according to the reason for the failure, and re-apply for the service.

[0165] As another embodiment, when detecting that a data storage component has a storage operation of requesting service information, a parameter sampling algorithm for determining the service requested by the target user in the requesting service information may include:

[0166] Obtain the storage notification message initiated by the data storage component when storing request service information through the resource controller;

[0167] Based on the stored notification message, a parameter sampling algorithm for the service requested by the target user in the service request information is determined.

[0168] The server can configure a resource controller and obtain the storage notification message initiated by the data storage component when storing the service request information. Through the storage notification message, the parameter sampling algorithm of the service requested by the target user in the service request information can be determined.

[0169] As yet another embodiment, in response to a sample acquisition request initiated by a target user, before calling a parameter sampling algorithm to generate a test sample, the method may further include:

[0170] Receive a sample acquisition request initiated by the target user for the parameter sampling algorithm.

[0171] In some embodiments, after determining the simulation result of the test sample based on the preset objective function, the method may further include:

[0172] Obtaining a judgment result on whether the test sample meets the preset convergence condition;

[0173] If the judgment result is that the test sample meets the convergence condition, the target sample is determined based on the test sample.

[0174] If the judgment result is that the test sample does not meet the convergence condition, the process returns to responding to the sample acquisition request initiated by the target user, calling the parameter sampling algorithm to generate the test sample and continue execution.

[0175] Optionally, based on the test sample, determining the target sample may include:

[0176] Obtain historical test samples corresponding to N sample acquisition requests before the test sample, and based on the simulation results corresponding to the test sample and the N historical test samples, select a target sample with the highest simulation result from the test sample and the N historical test samples.

[0177] The simulation result may specifically be a result index data. The higher the result index data is, the better the simulation result is; the lower the simulation result is, the worse the simulation result is.

[0178] In some embodiments, whether the test sample meets the preset convergence condition can be determined by whether the number of iterations corresponding to the test sample reaches a preset iteration threshold. If so, it is determined that the test sample meets the preset convergence condition. If not, it is determined that the test sample does not meet the preset convergence condition.

[0179] In certain embodiments, whether a test sample satisfies a preset convergence condition can be determined by determining whether a simulation result of the test sample satisfies a preset result threshold. If so, it is determined that the test sample has met the preset convergence condition; if not, it is determined that the test sample has not met the preset convergence condition. Whether the simulation result satisfies the preset result threshold can specifically include whether the simulation result is greater than the preset result threshold, or whether the simulation result is less than the preset result threshold. Whether the simulation result is greater than the result threshold or less than the result threshold can be determined based on the computational meaning of the objective function.

[0180] In order to improve the efficiency of parameter processing, multiple test samples can be generated at one time in a batch processing manner.

[0181] In some embodiments, in response to a sample acquisition request initiated by a target user, calling a parameter sampling algorithm to generate a test sample may include:

[0182] In response to a sample acquisition request initiated by a target user, a parameter sampling algorithm is called in a batch processing manner to generate multiple test samples.

[0183] Based on the preset objective function, determining the simulation results of the test sample may include:

[0184] Based on the preset objective function, the simulation results corresponding to the multiple test samples are determined.

[0185] The simulation results of the test samples output for the target user may include:

[0186] Output simulation results corresponding to multiple test samples for the target user.

[0187] Optionally, when determining the simulation results corresponding to multiple test samples based on a preset objective function, if it is a public cloud, the multiple test samples can be sent to the user end, and the sample simulation of the multiple test samples can be completed on the user end. If it is a private cloud, the sample simulation of the multiple test samples can be completed directly on the cloud.

[0188] Optionally, based on a preset objective function, determining the simulation results corresponding to the plurality of test samples may specifically include: inputting the plurality of test samples into the objective function respectively, and calculating to obtain the simulation results corresponding to the plurality of test samples respectively.

[0189] In some embodiments, the step of obtaining the simulation results can be performed on the cloud server or on the user end, and the specific setting can be set according to actual use requirements. When either the server end or the user end obtains the simulation results, the simulation results can be sent to the other end.

[0190] In one possible design, based on a preset objective function, determining simulation results corresponding to a plurality of test samples may include:

[0191] Create multiple simulation modules for the target function.

[0192] Match target simulation modules to multiple test samples from multiple simulation modules respectively;

[0193] Input any test sample into the target simulation module corresponding to the test sample, calculate and obtain the simulation result of the test sample, and obtain the simulation results corresponding to multiple test samples respectively.

[0194] In another possible design, based on a preset objective function, determining simulation results corresponding to the plurality of test samples may include:

[0195] Sending multiple test samples to a user terminal of a target user, so that the user terminal can input the multiple test samples into a preset objective function and calculate and obtain simulation results corresponding to the multiple test samples;

[0196] Receive simulation results corresponding to multiple test samples sent by the user end.

[0197] In some embodiments, the method may further include: collecting the simulation results of each test sample through the SideCar collection method in K8S, and using etcd to store the simulation results of each test sample.

[0198] The technical solutions of the embodiments of this application can be applied in many fields to solve parameter optimization problems. In the allocation process of power resources or water resources, the allocation results of power resources or water resources in various regions can be used as a parameter to be processed to initiate a parameter optimization request. The parameter to be processed can specifically be the amount of resources corresponding to each region, for example, in the power scenario, it can be the load capacity of the region.

[0199] As an embodiment, detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user may include:

[0200] Receive a parameter optimization request initiated by a target user for the pending parameters of a target resource;

[0201] Determine a parameter sampling algorithm that matches the processing objectives of the target resource;

[0202] In response to a sample acquisition request initiated by a target user, calling a parameter sampling algorithm to generate a test sample may include:

[0203] In response to a sample acquisition request initiated by a target user for parameters to be processed, a parameter sampling algorithm is called to generate a test sample of the parameters to be processed;

[0204] The simulation results of the test samples output for the target user may include:

[0205] Output the simulation results corresponding to the test samples of the parameters to be processed to the target user, so that the target user can process the target resources according to the test samples.

[0206] Optionally, the target resources may include power resources, water resources, data resources, etc. The embodiments of the present application do not impose too many restrictions on the specific form and content of the resources.

[0207] The resource element specifically represented by the parameter to be processed can be determined according to the processing target of the target resource. For example, when the processing target of the target resource can be the power load capacity set for different regions to minimize the total energy consumption of the power grid, the power load capacity of different regions can be the parameter to be processed, and the processing target can be the calculation function of the total energy consumption of the power grid. The target parameter can be the power load capacity of each region when the total energy consumption of the power grid is minimized. According to the value of the parameter to be processed in the target parameter, the processing information of the target resource can be generated, that is, according to the value of the processing parameter in the target parameter, the prompt information or setting instructions of the power load capacity of each region can be generated, and the capacity can be set according to the power load capacity of each region through the setting instructions. The prompt information can be displayed to the user so that the user can set the capacity of each region according to the power load capacity of each region prompted in the prompt information.

[0208] In the field of e-commerce, parameter optimization issues are also involved. Taking the more common product recommendation as an example, due to the differences in the user's browsing characteristics such as consumption habits, areas of interest, historical browsing behavior, etc., the content or products recommended to the user are also different. In actual applications, in order to improve the user's click-through rate, the user's browsing characteristics such as consumption habits and areas of interest can be parameterized to generate different browsing parameters, and by setting multiple browsing parameters, the characteristics of the user's click target can be accurately analyzed, so as to find the target product with higher user attention. The solution of sampling multiple browsing parameters and conducting parameter tests to determine the user's click probability can be applied to the technical solution of the embodiment of the present application to improve the test efficiency.

[0209] Therefore, as an embodiment, detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user may include:

[0210] receiving a parameter optimization request for browsing parameters generated for a browsing operation initiated by a target user;

[0211] Determine a parameter sampling algorithm that matches the browsing goals of target users;

[0212] Optionally, in response to a sample acquisition request initiated by a target user, calling a parameter sampling algorithm to generate a test sample may include:

[0213] In response to a sample acquisition request initiated by a target user for browsing parameters, a parameter sampling algorithm is called to generate a test sample of the browsing parameters;

[0214] The simulation results of the test samples output for the target user may include:

[0215] Output the simulation results corresponding to the test samples of the browsing parameters to the target user, so that the target user can configure the browsing parameters according to the test samples.

[0216] like Figure 5 FIG. 1 is a flowchart of another embodiment of an information processing method provided by an embodiment of the present application. The method may include:

[0217] 501: Detects parameter optimization requests initiated by the target user for the parameter sampling algorithm.

[0218] The technical solutions of the embodiments of the present application can be applied to the user end, which can be, for example, a mobile phone terminal, a computer, a notebook, a tablet computer, a virtual reality / augmented reality device, an Internet of Things (IoT) terminal, and other electronic devices. The embodiments of the present application do not impose too many restrictions on the specific types of electronic devices.

[0219] The specific content and technical effects executed by the user terminal have been described in detail in the above embodiments and will not be repeated here.

[0220] 502: Send a parameter optimization request to the server so that the server can determine the parameter sampling algorithm that matches the target user;

[0221] 503: Send the sample acquisition request initiated by the target user to the server, so that the server can respond to the sample acquisition request and call the parameter sampling algorithm to generate test samples.

[0222] 504: Determine a simulation result of the test sample based on a preset objective function.

[0223] 505: Output the simulation results of the test samples to the target user.

[0224] Optionally, the objective function may belong to a black-box algorithm, in which case the parameter optimization request is a black-box optimization request.

[0225] In an embodiment of the present application, the user end can detect the parameter optimization request initiated by the target user for the parameter sampling algorithm. Thus, the parameter optimization request is sent to the server end. When the server end receives the parameter optimization request sent by the user end, it can determine the parameter sampling algorithm corresponding to the target user. Afterwards, the user end can also send a sample acquisition request initiated by the target user to the server end. When the server end receives the sample acquisition request, it can call the parameter sampling algorithm to generate a test sample. And based on the preset objective function, the simulation result of the test sample is determined, and the simulation result of the test sample is output to the target user. The user end provides the target user with sample parameter generation and sample parameter simulation work, and realizes parameter optimization service through interaction with the target user, so that the target user can select the parameter sampling algorithm for parameter optimization at any time, thereby improving the utilization efficiency of the black box algorithm.

[0226] Optionally, based on a preset objective function, determining the simulation result of the test sample may include: receiving the test sample sent by the server, and inputting the test sample into the objective function to calculate and obtain the simulation result of the test sample.

[0227] Optionally, based on a preset objective function, determining a simulation result of the test sample may include: receiving a simulation result of the test sample sent by a server, wherein the simulation result is obtained by inputting the test sample into a simulation function for calculation.

[0228] As an embodiment, determining the simulation result of the test sample based on the preset objective function may include:

[0229] Receive test samples sent by the server;

[0230] The test sample is input into the objective function, and the calculation result corresponding to the test sample is obtained.

[0231] In one possible design, receiving the test sample sent by the server may include:

[0232] Receiving multiple test samples sent by the server; wherein the multiple test samples are generated by the server calling the parameter sampling algorithm in a batch mode;

[0233] Based on the preset objective function, determining the simulation results of the test sample may include:

[0234] Multiple test samples are input into the objective function respectively, and the calculation results corresponding to the multiple test samples are obtained respectively.

[0235] As yet another embodiment, determining the simulation result of the test sample based on a preset objective function includes:

[0236] Receive the simulation result corresponding to the test sample sent by the server; wherein the simulation result is obtained by the server inputting the test sample into the preset objective function for calculation.

[0237] In some embodiments, after determining the simulation result of the test sample based on the preset objective function, the method may further include:

[0238] Obtain the judgment result of whether the test sample meets the convergence condition;

[0239] If the judgment result is that the test sample meets the convergence condition, then the target sample is determined based on the test sample;

[0240] If the judgment result is that the test sample does not meet the convergence condition, it returns to sending the sample acquisition request initiated by the target user to the server, so that the server can respond to the sample acquisition request and call the parameter sampling algorithm to generate the test sample to continue execution.

[0241] Optionally, based on the test sample, determining the target sample may include:

[0242] Obtain historical test samples corresponding to N sample acquisition requests before the test sample, and based on the simulation results corresponding to the test sample and the N historical test samples, select a target sample with the highest simulation result from the test sample and the N historical test samples.

[0243] The simulation result may be a result index data. The higher the result index data, the better the simulation result. The smaller the result index data, the worse the simulation result.

[0244] It should be noted that, for some steps in the embodiments of the present application, the specific steps executed are the same when executed on the user side or on the server side. The specific implementation method and technical effects of each step have been described in detail in the aforementioned embodiments and will not be repeated here.

[0245] like Figure 6 FIG. 1 is a flowchart of another embodiment of an information processing method provided by an embodiment of the present application. The method may include:

[0246] 601: In response to a request to call an information processing interface, determine processing resources corresponding to the information processing interface.

[0247] Use the processing resources corresponding to the information processing interface to perform the following steps:

[0248] 602: Detect the parameter optimization request initiated by the target user and determine a parameter sampling algorithm that matches the target user.

[0249] 603: In response to the sample acquisition request initiated by the target user, a parameter sampling algorithm is called to generate a test sample.

[0250] 604: Determine a simulation result of the test sample based on a preset objective function.

[0251] 605: Output the simulation results of the test sample to the target user.

[0252] The specific steps executed by the processing resources corresponding to the information processing interface in the embodiment of the present application are similar to those in the embodiment of the present invention. Figures 1 to 4 The processing steps performed by the information processing method shown are the same, and the specific implementation methods and technical effects of each technical feature have been Figures 1 to 4 The embodiments shown are described in detail and will not be repeated here.

[0253] In practical applications, the target user's user terminal can be, for example, a mobile phone terminal, a computer, a notebook, a tablet computer, a virtual reality / augmented reality device, an Internet of Things (IoT) terminal, or other electronic device. The specific type of electronic device is not particularly limited in the embodiments of the present application. The user terminal can interact with the user and communicate with a server capable of optimizing parameters.

[0254] For ease of understanding, the parameters that need to be optimized are the hyperparameters consisting of the network depth, number of iterations, and number of neurons in each layer of the machine learning model. The cloud service provides an information processing method and introduces an application example of an embodiment of the present application in detail by taking interaction with the user end as an example.

[0255] refer to Figure 7 For example, the user end is a mobile terminal M1 and the server is a cloud server M2. Mobile terminal M1 can detect 71 a parameter optimization request initiated by a user for hyperparameters consisting of network depth, number of iterations, and number of neurons per layer of a machine learning model. Mobile terminal M1 can send 702 the parameter optimization request to cloud server M2. Upon detecting the parameter optimization request, cloud server M2 can determine 703 a parameter sampling algorithm that matches the target user.

[0256] Afterwards, the mobile terminal M2 may detect 704 the sample acquisition request initiated by the target user and send 705 the sample acquisition request to the cloud server M2.

[0257] Afterwards, the cloud server M2 can respond to the sample acquisition request initiated by the target user and call the parameter sampling algorithm to generate a test sample 706. The cloud server can also determine 707 the simulation result of the test sample based on the preset objective function and output 708 the simulation result of the test sample to the target user.

[0258] Optionally, the cloud server M2 outputting the simulation result of the test sample to the target user may include: generating a prompt page 7081 based on the simulation result of the test sample, and sending 7082 the prompt page to the mobile terminal M1. After receiving the prompt page, the mobile terminal M1 may display 7083 the prompt page on the display screen.

[0259] In addition, the simulation results of the test samples can also be output in the form of data strings, short messages or instant messaging messages. The embodiments of the present application do not impose too many restrictions on the specific output method of the simulation results.

[0260] The technical solutions of the embodiments of the present application can be applied to various fields such as artificial intelligence interaction, data retrieval, content recommendation, click-through rate prediction, smart factories, industrial control, etc., especially in the field of content recommendation, such as content recommendation in e-commerce, live video, social, and online education, and resource allocation, such as financial product configuration, power resources, water resources, supply chain distribution and other fields.

[0261] To facilitate understanding, the embodiments of the present application are introduced in detail using the following problem cases in actual field scenarios as examples.

[0262] (1) E-commerce field. In the e-commerce field, application scenarios such as feature search, product recommendation in live broadcast scenarios, content recommendation, and calculation of advertising click-through rate are the most common. This embodiment takes the content recommendation scenario as an example and conducts an example deployment. The general recommendation process in the recommendation scenario can be to parameterize the elements of the selected scenario, obtain the parameters that affect the scenario, and use the parameters to identify the different features of the scenario. The server can display a variety of black box algorithms for the target user and describe the functions and effects of each black box algorithm in detail. The target user can select a parameter sampling algorithm from multiple black box algorithms. And initiate a parameter optimization request to the server through the user terminal. When the server receives the parameter optimization request initiated by the target user, it can determine the parameter sampling algorithm selected by the target user.

[0263] During the parameter optimization process, the parameters need to be tested multiple times to obtain the target parameters. During any parameter test, the target user can initiate a sample acquisition request corresponding to the parameters that match the recommendation scenario through the user end. At this time, the server end can respond to the sample acquisition request initiated by the target user and call the parameter sampling algorithm to generate a test sample. Afterwards, based on the preset objective function, the simulation result of the test sample is determined. After the server end determines the simulation result, it can send the simulation result to the user end, and the user end will display the simulation result of the test sample to the target user. The target user can judge whether the test sample can be used by viewing the simulation result. If the test sample is judged by the target user to meet the usage conditions, the target user can use the test sample to set the recommendation elements and recommend content to the user according to the recommendation elements.

[0264] Taking the click word recommendation scenario as an example, when a user clicks on the search box in the APP (Application), the system will recommend some search words (Query words) to the user. The purpose of recommending search words to users is to explore the user's potential purchasing needs, increase the user's usage stickiness and increase the total number of commodity transactions. The search system uses the following architecture, combined with a deep learning Encode-Decode (encoder-decoder) network, that is, the target network, to predict the recommendation of search words. Assume that the target parameter is selected for the number of search words. In the prior art, the parameter value of the parameter to be optimized constituted by the number of search words is manually set according to human experience. Using the data processing method of this patent, the number of search words can be automatically tested for parameters according to the above parameter optimization process. The test sample obtained by the server is the number of search words, and the simulation result of the test sample is the click rate or transaction rate obtained after setting according to the number of search words.

[0265] (2) Social field. In the social field, it is common to recommend content to social users and materials to students. Recommendations in the social field usually involve social users browsing social applications, and the application's display interface displays social content that the user is interested in. Generally, recommendations in the social field are usually based on options such as the user's historical browsing behavior, areas of interest, and user information to form feature parameters. Combinations of different options can constitute parameters to be processed. When the test sample corresponding to the parameter to be processed is determined, social content can be recommended according to the test sample. In order to find content that social users are interested in, the number and type of parameters can be optimized to obtain accurate social user content for testing.

[0266] The technical solution of the embodiments of this application can be deployed in a cloud server. Parameter optimization requests can be initiated by operations and maintenance personnel, who can use user information, social type, and other parameters as parameters to be processed and continuously generate test samples using a parameter sampling algorithm. By simulating the effects of the test samples, simulation results for the test parameters are obtained, allowing target samples to be selected from multiple test samples. Feature parameters for social content recommendation are then set based on the target samples, achieving accurate recommendations.

[0267] (3) Financial field. The stock index simulation is a very important issue. The simulation problem of stock index based on models such as linear regression, SVM (support vector machines) and LSTM (Long Short-Term Memory) is relatively common. Before using the model, a suitable model needs to be established first. Among them, the model training process may involve many hyperparameters, such as time_step (time step), feature_dim (feature dimension), hidden features (hidden features), etc. in LSTM, and also involves macro factors, micro factors, emergencies and other contextual features of the market. These contextual features will affect the selection of parameters. Using this patented technology, test samples can be generated for the hyperparameters that need to be set in the financial field, and the corresponding simulation results can be obtained by simulating the test samples.

[0268] The simulation results are output to the target user for review. When the target user selects a target sample with a good simulation result from a large number of test samples, they use the target sample to build a machine learning model for the index simulation problem, perform model training, and obtain model parameters. The trained machine learning model is then used to simulate and calculate data such as the RMSE (Root Mean Squared Error) difference of the actual stock index for the index simulation problem.

[0269] (4) Resource allocation: Take the allocation of electricity resources as an example. The allocation of electricity resources usually involves many regions. Each region can be represented by corresponding parameters, and these parameters can allocate a certain proportion of resources. The allocation of resources will affect regional economic, population, environmental and other information.

[0270] The technical solution of the embodiment of the present application can be applied to the problem of dynamic pricing in the power market and the problem of power economic load distribution.

[0271] In the problem of dynamic pricing in the electricity market, the type of user and the amount of electricity consumed are key factors influencing the electricity market. Parameters such as user type and electricity consumption can be used as parameters to be processed to initiate a parameter optimization request. In response to the parameter optimization request, after determining the parameter sampling algorithm, the parameter sampling algorithm can be used to generate test samples of the parameters to be processed. The setting of the candidate parameters can serve as the ultimate optimization target for the benefit / cost of the power system to determine the objective function corresponding to the optimization target. The objective function can be used to simulate the usage results of the test samples to obtain simulation results, which represent the value of the system's benefit / cost. Subsequently, by continuously generating test samples and simulating the test samples, a target sample can be selected from many test samples.

[0272] In the problem of power economic load distribution, the power supplier can provide power resources to multiple regions at the same time. The power load capacity of each region can be used as a candidate parameter, and the total energy consumption of the power grid can be used as the output of the objective function. Using the technical solution of the embodiment of the present application, the target user can initiate a parameter optimization request for the power load capacity of each region as a parameter to be processed. After determining the parameter sampling algorithm that matches the parameter optimization request of the target user, the sample acquisition request initiated by the target user can be received to call the parameter sampling algorithm to continuously review the test samples corresponding to the test values ​​of the power load capacity of each region. In the field of power load distribution, the objective function can be a nonlinear constraint relationship between the power load capacity and the total energy consumption of the power grid. The objective function can be used to simulate the test sample to obtain a simulation result. Afterwards, by continuously simulating the test samples of the power load capacity of each region, the highest simulation result is selected from them, and the test sample corresponding to the highest simulation result can be used to generate a load capacity allocation strategy.

[0273] For ease of understanding, the technical solutions of the embodiments of this application are described in detail using the field of e-commerce as an example. Figure 8 FIG. 1 is a flowchart of an embodiment of an information processing method provided by an embodiment of the present application. The method may include the following steps:

[0274] 801: Receive a parameter optimization request initiated by a target user for the to-be-processed parameters of a target resource.

[0275] 802: Determine a parameter sampling algorithm that matches the processing goal of the target resource.

[0276] 803: In response to a sample acquisition request initiated by a target user for the parameter to be processed, a parameter sampling algorithm is invoked to generate a test sample of the parameter to be processed.

[0277] 804: Determine a simulation result of the test sample based on a preset objective function.

[0278] 805: Output simulation results corresponding to the test samples of the parameters to be processed to the target user, so that the target user can process the target resources according to the test samples.

[0279] During the allocation process of power resources and water resources, the allocation results of power resources or water resources in various regions can be used as a parameter to be processed to initiate a parameter optimization request. The parameter to be processed can specifically be the resource amount corresponding to each region. For example, in the power scenario, it can be the load capacity of the region.

[0280] Optionally, the target resources may include power resources, water resources, data resources, etc. The embodiments of the present application do not impose too many restrictions on the specific form and content of the resources.

[0281] Optionally, the resource element specifically represented by the parameter to be processed can be determined according to the processing target of the target resource. For example, when the processing target of the target resource can be the power load capacity set for different regions to minimize the total energy consumption of the power grid, the power load capacity of different regions can be the parameter to be processed, and the processing target can be the calculation function of the total energy consumption of the power grid. The target parameter can be the power load capacity of each region when the total energy consumption of the power grid is minimized. According to the value of the parameter to be processed in the target parameter, the processing information of the target resource can be generated, that is, according to the value of the processing parameter in the target parameter, the prompt information or setting instructions of the power load capacity of each region can be generated, and the capacity can be set according to the power load capacity of each region through the setting instructions. The prompt information can be displayed to the user so that the user can set the capacity of each region according to the power load capacity of each region prompted in the prompt information.

[0282] For ease of understanding, the technical solution of the embodiment of this application is described in detail using the resource processing scenario as an example. Figure 9 FIG. 1 is a flowchart of an embodiment of an information processing method provided by an embodiment of the present application. The method may include the following steps:

[0283] 901: receiving a parameter optimization request for browsing parameters corresponding to a browsing operation initiated by a target user;

[0284] 902: Determine a parameter sampling algorithm that matches the browsing goal of the target user.

[0285] 903: In response to the sample acquisition request initiated by the target user for the browsing parameters, a parameter sampling algorithm is called to generate a test sample of the browsing parameters.

[0286] 904: Determine a simulation result of the test sample based on a preset objective function.

[0287] 905: Outputting simulation results corresponding to the test sample of the browsing parameters to the target user, so that the target user can configure the browsing parameters according to the test sample.

[0288] In the field of e-commerce, parameter optimization issues are also involved. Taking the more common product recommendation as an example, due to the differences in the user's browsing characteristics such as consumption habits, areas of interest, historical browsing behavior, etc., the content or products recommended to the user are also different. In actual applications, in order to improve the user's click-through rate, the user's browsing characteristics such as consumption habits and areas of interest can be parameterized to generate different browsing parameters, and by setting multiple browsing parameters, the characteristics of the user's click target can be accurately analyzed, so as to find the target product with higher user attention. The solution of sampling multiple browsing parameters and conducting parameter tests to determine the user's click probability can be applied to the technical solution of the embodiment of the present application to improve the test efficiency.

[0289] like Figure 10 FIG. 1 is a schematic diagram of a structure of an information processing device according to an embodiment of the present application. The device may include:

[0290] Request detection module 1001: used to detect the parameter optimization request initiated by the target user and determine the parameter sampling algorithm that matches the target user.

[0291] The first response module 1002 is configured to respond to a sample acquisition request initiated by a target user and invoke a parameter sampling algorithm to generate a test sample.

[0292] The first simulation module 1003 is used to determine the simulation result of the test sample based on a preset objective function.

[0293] The first output module 1004 is used to output the simulation results of the test sample to the target user.

[0294] In an embodiment of the present application, the parameter optimization request initiated by the target user can be detected, and the parameter sampling algorithm that matches the target user can be determined. By providing an external black box service, the target user can use the black box algorithm to optimize the parameters at any time. After the parameter sampling algorithm is called to generate a test sample in response to the sample acquisition request initiated by the target user, the simulation result of the test sample can be determined based on the preset objective function, and the test sample can be automatically generated for the target user, and the simulation calculation of the test sample can be completed. Through interaction with the target user, a cloud service for parameter optimization is realized to achieve rapid parameter optimization in the cloud and improve the efficiency of parameter optimization. In addition, by obtaining the user's black box service request parameter optimization request and sample acquisition request, the user's service needs can be obtained, and by effectively responding to and providing feedback on the user's service needs, the user can be effectively provided with a black box service, the extended application of the black box service can be realized, and the utilization efficiency of the black box algorithm can be improved.

[0295] As an embodiment, the first simulation module may include:

[0296] The first sending unit is configured to send the test sample to a user terminal of a target user, so that the user terminal can input the test sample into a preset objective function and calculate a simulation result corresponding to the test sample;

[0297] The first receiving unit is configured to receive a simulation result corresponding to a test sample sent by a user terminal.

[0298] As yet another embodiment, the first simulation module may include:

[0299] The first calculation unit is used to input the test sample into a preset objective function and calculate and obtain the simulation result of the test sample.

[0300] In some embodiments, the apparatus may further include:

[0301] A node determination unit, used to determine a target node for starting a parameter sampling algorithm;

[0302] The first response module may include:

[0303] a first response unit, configured to respond to the sample acquisition request and send the sample acquisition request to a target node for starting the parameter sampling algorithm;

[0304] The sample acquisition unit is used to acquire the test samples generated by the parameter sampling algorithm through the target node.

[0305] In one possible design, the first computing unit may include:

[0306] A module building unit, used for building a simulation module for the target function;

[0307] The module calculation unit is used to input the test sample into the simulation module and calculate the simulation result of the test sample.

[0308] As yet another embodiment, the device may further include:

[0309] An identification receiving module, used for receiving a simulation test identification sent by a target user;

[0310] The identification marking module is used to store the simulation results of the test samples for the target user based on the simulation test identification.

[0311] In some embodiments, the request detection module may include:

[0312] A request receiving unit, configured to receive a parameter optimization request sent by a target user; wherein the parameter optimization request includes request service information for a parameter sampling algorithm;

[0313] The first storage unit is used to determine a parameter sampling algorithm for the service requested by the target user in the service request information when detecting that a storage operation of the service request information exists in the data storage component.

[0314] As a possible implementation, the device may further include:

[0315] A first verification unit is configured to verify the parameter optimization request of the target user based on the verification information in the service request information, and obtain a verification result;

[0316] The second storage unit is configured to store the requested service information in the data storage component if the verification result is successful.

[0317] In some embodiments, the first storage unit may be specifically used for:

[0318] Obtain the storage notification message initiated by the data storage component when storing request service information through the resource controller;

[0319] Based on the stored notification message, a parameter sampling algorithm for the service requested by the target user in the service request information is determined.

[0320] As an embodiment, the device may further include:

[0321] The convergence judgment module is used to obtain the judgment result of whether the test sample meets the preset convergence conditions;

[0322] A first processing module is configured to determine a target sample based on the test sample if the result of the judgment is that the test sample meets the convergence condition;

[0323] The second processing module is configured to jump to the first response module for further execution if the judgment result is that the test sample does not meet the convergence condition.

[0324] In one possible design, the first response module may include:

[0325] A second response unit is configured to respond to a sample acquisition request initiated by a target user and call a parameter sampling algorithm in a batch processing manner to generate a plurality of test samples;

[0326] The first simulation module may include:

[0327] A first simulation unit is used to determine simulation results corresponding to a plurality of test samples based on a preset objective function;

[0328] The first output module may include:

[0329] The first output unit is used to output simulation results corresponding to multiple test samples for the target user.

[0330] In yet another possible design, the first simulation module may include:

[0331] A simulation establishment unit, used for establishing multiple simulation modules for the target function;

[0332] A simulation matching module matches target simulation modules for multiple test samples from multiple simulation modules;

[0333] The second simulation module is used to input any test sample into the target simulation module corresponding to the test sample, calculate and obtain the simulation result of the test sample, so as to obtain simulation results corresponding to multiple test samples respectively.

[0334] Further, optionally, the first simulation unit may be specifically configured to:

[0335] Send multiple test samples to the user terminal of the target user, so that the user terminal can input the multiple test samples into the preset objective function respectively, and calculate the simulation results corresponding to the multiple test samples respectively; receive the simulation results corresponding to the multiple test samples sent by the user terminal.

[0336] As an embodiment, the request detection module may include:

[0337] The second receiving unit is configured to receive a parameter optimization request initiated by a target user for parameters to be processed of a target resource.

[0338] a first determining unit, configured to determine a parameter sampling algorithm that matches a processing target of a target resource;

[0339] The first response module may include:

[0340] A request response unit, configured to respond to a sample acquisition request initiated by a target user for parameters to be processed, and call a parameter sampling algorithm to generate a test sample of the parameters to be processed;

[0341] The first output module may include:

[0342] The second output unit is used to output simulation results corresponding to the test samples of the parameters to be processed to the target user, so that the target user can process the target resources according to the test samples.

[0343] As yet another embodiment, the request detection module may include:

[0344] a third receiving unit, configured to receive a parameter optimization request for browsing parameters generated by a browsing operation initiated by a target user;

[0345] A second determining unit is used to determine a parameter sampling algorithm that matches the browsing target of the target user;

[0346] The first response module may include:

[0347] The second request response unit is used to respond to the sample acquisition request initiated by the target user for the browsing parameters and call the parameter sampling algorithm to generate a test sample of the browsing parameters;

[0348] The first output module may include:

[0349] The third output unit is configured to output simulation results corresponding to the test samples of the browsing parameters to the target user, so that the target user can configure the browsing parameters according to the test samples.

[0350] In some embodiments, the objective function belongs to a black box algorithm; the request detection module can be specifically used to:

[0351] A black box optimization request initiated by the target user is detected, and a parameter sampling algorithm matching the target user is determined.

[0352] Figure 10 The information processing device can execute Figure 1 The specific manner of each step executed by each module and unit in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0353] In practical applications, Figure 10 The information processing device shown can be configured as a server. Figure 11 , is a structural diagram of an embodiment of a server provided in an embodiment of the present application, the server may include: a storage component 1101 and a processing component 1102; the storage component is used to store one or more computer instructions; the one or more computer instructions are called by the processing component;

[0354] The processing component 1102 can be used to:

[0355] Detect the parameter optimization request initiated by the target user and determine the parameter sampling algorithm that matches the target user; in response to the sample acquisition request initiated by the target user, call the parameter sampling algorithm to generate a test sample; based on the preset objective function, determine the simulation result of the test sample; output the simulation result of the test sample to the target user.

[0356] In an embodiment of the present application, the parameter optimization request initiated by the target user can be detected, and the parameter sampling algorithm that matches the target user can be determined. By providing an external black box service, the target user can use the black box algorithm to optimize the parameters at any time. After the parameter sampling algorithm is called to generate a test sample in response to the sample acquisition request initiated by the target user, the simulation result of the test sample can be determined based on the preset objective function, and the test sample can be automatically generated for the target user, and the simulation calculation of the test sample can be completed. Through interaction with the target user, a cloud service for parameter optimization is realized to achieve rapid parameter optimization in the cloud and improve the efficiency of parameter optimization. In addition, by obtaining the user's black box service request parameter optimization request and sample acquisition request, the user's service needs can be obtained, and by effectively responding to and providing feedback on the user's service needs, the user can be effectively provided with a black box service, the extended application of the black box service can be realized, and the utilization efficiency of the black box algorithm can be improved.

[0357] In addition, the processing component can also execute the information processing method shown in any of the aforementioned embodiments, which will not be described in detail for the sake of brevity. The server in the embodiment of the present application can be the server of the aforementioned embodiment, and can interact with the user device corresponding to the user end for data or information.

[0358] The processing component 1102 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above information processing method.

[0359] The storage component 1101 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0360] Of course, the server may also include other components, such as input / output interfaces and communication components. The input / output interface provides an interface between the processing component and peripheral interface modules, such as output devices and input devices. The communication component is configured to facilitate wired or wireless communication between the server and other devices, such as user devices.

[0361] In addition, the embodiment of the present application also provides a computer-readable storage medium, which can store one or more computer instructions, which are used to implement Figures 1 to 4 The information processing method described in the embodiments.

[0362] like Figure 12 FIG. 1 is a schematic diagram of a structure of an information processing device according to an embodiment of the present application. The device may include:

[0363] Request initiation module 1201: used to detect the parameter optimization request initiated by the target user for the parameter sampling algorithm.

[0364] The first sending module 1202 is used to send the parameter optimization request provided by the target user to the server, so that the server can determine the parameter sampling algorithm that matches the target user;

[0365] The second sending module 1203 is used to send the sample acquisition request initiated by the target user to the server, so that the server responds to the sample acquisition request and calls the parameter sampling algorithm to generate a test sample.

[0366] The second simulation module 1204 is used to determine the simulation result of the test sample based on a preset objective function.

[0367] The second output module 1205 is used to output the simulation results of the test sample to the target user.

[0368] In an embodiment of the present application, the user end can detect the parameter optimization request initiated by the target user for the parameter sampling algorithm. Thus, the parameter optimization request is sent to the server end. When the server end receives the parameter optimization request sent by the user end, it can determine the parameter sampling algorithm corresponding to the target user. Afterwards, the user end can also send a sample acquisition request initiated by the target user to the server end. When the server end receives the sample acquisition request, it can call the parameter sampling algorithm to generate a test sample. And based on the preset objective function, the simulation result of the test sample is determined, and the simulation result of the test sample is output to the target user. The user end provides the target user with sample parameter generation and sample parameter simulation work, and realizes parameter optimization service through interaction with the target user, so that the target user can select the parameter sampling algorithm for parameter optimization at any time, thereby improving the utilization efficiency of the black box algorithm.

[0369] As an embodiment, the second simulation module may include:

[0370] A sample receiving unit, used to receive test samples sent by the server;

[0371] The sample simulation unit is used to input the test sample into the objective function and calculate the calculation result corresponding to the test sample.

[0372] In some embodiments, the sample receiving unit may be specifically configured to: receive a plurality of test samples sent by a server; wherein the plurality of test samples are generated by the server by calling a parameter sampling algorithm in a batch processing manner.

[0373] The sample simulation unit can be specifically used to: input multiple test samples into the objective function respectively, and calculate and obtain calculation results corresponding to the multiple test samples respectively.

[0374] As yet another embodiment, the second simulation module may include:

[0375] The result receiving unit is used to receive the simulation result corresponding to the test sample sent by the server; wherein the simulation result is obtained by the server by inputting the test sample into a preset objective function for calculation.

[0376] In some embodiments, the apparatus may further include:

[0377] The convergence judgment module is used to obtain the judgment result of whether the test sample meets the preset convergence conditions;

[0378] A first processing module is configured to determine a target sample based on the test sample if the result of the judgment is that the test sample meets the convergence condition;

[0379] The second processing module is configured to jump to the second sending module for further execution if the judgment result is that the test sample does not meet the convergence condition.

[0380] Figure 12 The information processing device can execute Figure 5 The information processing method of the embodiment shown, its implementation principle and technical effects are not repeated here. The specific manner of each step executed by each module, device and unit in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0381] In practical applications, Figure 12 The information processing device shown can be configured as a user device. Figure 13, which is a structural diagram of an embodiment of a user device provided in an embodiment of the present application, the user device may include: a storage component 1301 and a processing component 1302; the storage component 1301 is used to store one or more computer instructions; and the one or more computer instructions are called by the processing component 1302.

[0382] The processing component 1302 can be used to:

[0383] Detect the parameter optimization request initiated by the target user for the parameter sampling algorithm; send the parameter optimization request provided by the target user to the server so that the server can determine the parameter sampling algorithm that matches the target user; send the sample acquisition request initiated by the target user to the server so that the server can respond to the sample acquisition request and call the parameter sampling algorithm to generate a test sample; determine the simulation result of the test sample based on the preset objective function; output the simulation result of the test sample to the target user.

[0384] In an embodiment of the present application, the user end can detect the parameter optimization request initiated by the target user for the parameter sampling algorithm. Thus, the parameter optimization request is sent to the server end. When the server end receives the parameter optimization request sent by the user end, it can determine the parameter sampling algorithm corresponding to the target user. Afterwards, the user end can also send a sample acquisition request initiated by the target user to the server end. When the server end receives the sample acquisition request, it can call the parameter sampling algorithm to generate a test sample. And based on the preset objective function, the simulation result of the test sample is determined, and the simulation result of the test sample is output to the target user. The user end provides the target user with sample parameter generation and sample parameter simulation work, and realizes parameter optimization service through interaction with the target user, so that the target user can select the parameter sampling algorithm for parameter optimization at any time, thereby improving the utilization efficiency of the black box algorithm.

[0385] The user equipment shown in the embodiments of the present application can specifically serve as the user end in the aforementioned embodiments. For the specific processing methods and beneficial effects of each step in the embodiments of the present application, please refer to the relevant description of the user end in the aforementioned embodiments, which will not be repeated here.

[0386] In addition, the processing component can also execute the information processing method shown in any of the aforementioned embodiments, which will not be repeated here for the sake of brevity.

[0387] The processing component 1302 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above information processing method.

[0388] The storage component 1301 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0389] Of course, the user device may also include other components, such as input / output interfaces and communication components. The input / output interface provides an interface between the processing component and peripheral interface modules, which may be output devices, input devices, etc. The communication component is configured to facilitate wired or wireless communication between the user device and other devices.

[0390] In addition, the embodiment of the present application further provides a computer-readable storage medium, which can store one or more computer instructions, which are used to implement the embodiment of the present application when executed. Figure 5 The information processing method of the illustrated embodiment.

[0391] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. That is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0392] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product. This application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0393] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An information processing method, characterized in that: Applied to the server, the method includes: Detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user; In response to a sample acquisition request initiated by the target user, calling the parameter sampling algorithm to generate a test sample; Determining a simulation result of the test sample based on a preset objective function; Outputting simulation results of the test sample to the target user; After determining the simulation result of the test sample based on the preset objective function, the method further includes: Obtaining a judgment result of whether the test sample meets a preset convergence condition; If the judgment result is that the test sample meets the convergence condition, determining a target sample based on the test sample; If the judgment result is that the test sample does not meet the convergence condition, the process returns to the step of responding to the sample acquisition request initiated by the target user, calling the parameter sampling algorithm to generate a test sample and continue execution.

2. The method according to claim 1, characterized in that Determining the simulation result of the test sample based on a preset objective function includes: Sending the test sample to a user terminal of the target user, so that the user terminal inputs the test sample into the preset objective function and calculates and obtains a simulation result corresponding to the test sample; Receive a simulation result corresponding to the test sample sent by the user terminal.

3. The method according to claim 1, characterized in that After detecting the parameter optimization request initiated by the target user and determining the parameter sampling algorithm that matches the target user, the method further includes: Determine a target node for starting the parameter sampling algorithm; The step of calling the parameter sampling algorithm to generate a test sample in response to the sample acquisition request initiated by the target user includes: In response to the sample acquisition request, sending the sample acquisition request to a target node for starting the parameter sampling algorithm; A test sample generated by the parameter sampling algorithm is obtained through the target node.

4. The method according to claim 1, wherein Determining the simulation result of the test sample based on a preset objective function includes: The test sample is input into the preset objective function, and a simulation result of the test sample is obtained by calculation.

5. The method according to claim 4, characterized in that Inputting the test sample into the preset objective function and calculating the simulation result of the test sample includes: Establishing a simulation module for the objective function; The test sample is input into the simulation module, and a simulation result of the test sample is obtained by calculation.

6. The method according to claim 1, characterized in that Also includes: receiving a simulation test identifier sent by the target user; Based on the simulation test identifier, the simulation result of the test sample is stored for the target user.

7. The method according to claim 1, characterized in that The detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user includes: Receiving a parameter optimization request sent by a target user; wherein the parameter optimization request includes request service information for a parameter sampling algorithm; When detecting that a data storage component has a storage operation for the service request information, a parameter sampling algorithm for the service requested by the target user in the service request information is determined.

8. The method according to claim 7, characterized in that The service request information also includes verification information; after receiving the parameter optimization request sent by the target user, the method further includes: Verifying the parameter optimization request of the target user based on the verification information in the service request information to obtain a verification result; If the verification result is successful, the requested service information is stored in the data storage component.

9. The method according to claim 7, characterized in that When the detection data storage component stores the service request information, the parameter sampling algorithm for determining the service requested by the target user in the service request information includes: Acquiring, through the resource controller, a storage notification message initiated by the data storage component when storing the requested service information; Based on the stored notification message, a parameter sampling algorithm for the service requested by the target user in the service request information is determined.

10. The method according to claim 1, characterized in that The objective function belongs to a black box algorithm; the detecting of the parameter optimization request initiated by the target user and determining the parameter sampling algorithm matching the target user includes: A black box optimization request initiated by the target user is detected, and a parameter sampling algorithm matching the target user is determined.

11. An information processing method, characterized in that: Applied to the server, the method includes: Receive a parameter optimization request initiated by a target user for pending parameters of a target resource; Determining a parameter sampling algorithm that matches the processing goal of the target resource; In response to a sample acquisition request initiated by the target user for the parameter to be processed, calling the parameter sampling algorithm to generate a test sample of the parameter to be processed; Determining a simulation result of the test sample based on a preset objective function; Outputting simulation results corresponding to the test samples of the parameters to be processed to the target user, so that the target user can process the target resource according to the test samples; After determining the simulation result of the test sample based on the preset objective function, the method further includes: Obtaining a judgment result of whether the test sample meets a preset convergence condition; If the judgment result is that the test sample meets the convergence condition, determining a target sample based on the test sample; If the judgment result is that the test sample does not meet the convergence condition, the process returns to the step of responding to the sample acquisition request initiated by the target user for the parameter to be processed, and calls the parameter sampling algorithm to generate the test sample of the parameter to be processed and continues to execute.

12. An information processing method, characterized in that: Applied to the server, the method includes: Receive a parameter optimization request for browsing parameters corresponding to a browsing operation initiated by a target user; Determining a parameter sampling algorithm that matches the browsing goal of the target user; In response to a sample acquisition request initiated by the target user for the browsing parameter, calling the parameter sampling algorithm to generate a test sample of the browsing parameter; Determining a simulation result of the test sample based on a preset objective function; Outputting simulation results corresponding to the test samples of the browsing parameters to the target user, so that the target user can configure the browsing parameters according to the test samples; After determining the simulation result of the test sample based on the preset objective function, the method further includes: Obtaining a judgment result of whether the test sample meets a preset convergence condition; If the judgment result is that the test sample meets the convergence condition, determining a target sample based on the test sample; If the judgment result is that the test sample does not meet the convergence condition, the process returns to the step of responding to the sample acquisition request initiated by the target user for the browsing parameter, calling the parameter sampling algorithm to generate the test sample of the browsing parameter and continuing the execution.

13. An information processing method, characterized in that: Applied to the server, the method includes: Detect parameter optimization requests initiated by target users for parameter sampling algorithms; Sending the parameter optimization request to a server, so that the server can determine a parameter sampling algorithm that matches the target user; Sending the sample acquisition request initiated by the target user to the server, so that the server responds to the sample acquisition request and calls the parameter sampling algorithm to generate a test sample; Determining a simulation result of the test sample based on a preset objective function; Outputting simulation results of the test sample to the target user; After determining the simulation result of the test sample based on the preset objective function, the method further includes: Obtaining a judgment result of whether the test sample meets a preset convergence condition; If the judgment result is that the test sample meets the convergence condition, determining a target sample based on the test sample; If the judgment result is that the test sample does not meet the convergence condition, the process returns to sending the sample acquisition request initiated by the target user to the server, so that the server responds to the sample acquisition request and calls the parameter sampling algorithm to generate a test sample for continued execution.

14. The method according to claim 13, characterized in that Determining the simulation result of the test sample based on a preset objective function includes: Receiving a test sample sent by the server; The test sample is input into the objective function, and a calculation result corresponding to the test sample is obtained by calculation.

15. The method according to claim 14, characterized in that The receiving the test sample sent by the server includes: Receiving a plurality of test samples sent by the server; wherein the plurality of test samples are generated by the server calling the parameter sampling algorithm in a batch processing manner; Determining the simulation result of the test sample based on a preset objective function includes: The multiple test samples are respectively input into the objective function, and calculation results corresponding to the multiple test samples are obtained respectively.

16. An information processing method, characterized in that: Applied to the server, the method includes: In response to a request to call an information processing interface, determining a processing resource corresponding to the information processing interface; The following steps are performed using the processing resources corresponding to the information processing interface: Detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user; In response to a sample acquisition request initiated by the target user, calling the parameter sampling algorithm to generate a test sample; Determining a simulation result of the test sample based on a preset objective function; Outputting simulation results of the test sample to the target user; After determining the simulation result of the test sample based on the preset objective function, the method further includes: Obtaining a judgment result of whether the test sample meets a preset convergence condition; If the judgment result is that the test sample meets the convergence condition, determining a target sample based on the test sample; If the judgment result is that the test sample does not meet the convergence condition, the process returns to the step of responding to the sample acquisition request initiated by the target user, calling the parameter sampling algorithm to generate a test sample and continue execution.

17. An information processing device, characterized in that: Applied to the server, the device includes: A request detection module is used to detect parameter optimization requests initiated by a target user and determine a parameter sampling algorithm that matches the target user; A first response module, configured to respond to a sample acquisition request initiated by the target user and call the parameter sampling algorithm to generate a test sample; A first simulation module is configured to determine a simulation result of the test sample based on a preset objective function; obtain a judgment result of whether the test sample satisfies a preset convergence condition; if the judgment result is that the test sample satisfies the convergence condition, determine a target sample based on the test sample; if the judgment result is that the test sample does not satisfy the convergence condition, return to the step of responding to the sample acquisition request initiated by the target user, invoke the parameter sampling algorithm to generate a test sample, and continue execution; The first output module is used to output the simulation result of the test sample to the target user.

18. An information processing device, characterized in that: Applied to the server, the device includes: The request initiation module is used to detect the parameter optimization request initiated by the target user for the parameter sampling algorithm; A first sending module is configured to send a parameter optimization request provided by a target user to a server, so that the server can determine a parameter sampling algorithm that matches the target user; A second sending module is configured to send the sample acquisition request initiated by the target user to the server, so that the server responds to the sample acquisition request and calls the parameter sampling algorithm to generate a test sample; A second simulation module is configured to determine a simulation result of the test sample based on a preset objective function; obtain a judgment result of whether the test sample satisfies a preset convergence condition; if the judgment result is that the test sample satisfies the convergence condition, determine a target sample based on the test sample; if the judgment result is that the test sample does not satisfy the convergence condition, return to sending a sample acquisition request initiated by the target user to the server, so that the server responds to the sample acquisition request and calls the parameter sampling algorithm to generate a test sample for continued execution; The second output module is used to output the simulation result of the test sample to the target user.

19. A server, characterized in that: include: A storage component and a processing component; the storage component is used to store one or more computer instructions; the one or more computer instructions are called by the processing component; The processing component is used to: Detecting a parameter optimization request initiated by a target user and determining a parameter sampling algorithm that matches the target user; in response to a sample acquisition request initiated by the target user, calling the parameter sampling algorithm to generate a test sample; Determining a simulation result of the test sample based on a preset objective function; Outputting a simulation result of the test sample to the target user; after determining the simulation result of the test sample based on the preset objective function, the processing component is further configured to: obtain a judgment result of whether the test sample meets a preset convergence condition; if the judgment result is that the test sample meets the convergence condition, determining a target sample based on the test sample; If the judgment result is that the test sample does not meet the convergence condition, the process returns to the step of responding to the sample acquisition request initiated by the target user, calling the parameter sampling algorithm to generate a test sample and continue execution.

20. A user equipment, characterized in that The system comprises: a storage component and a processing component; the storage component is used to store one or more computer instructions; the one or more computer instructions are called by the processing component; The processing component is used to: Detecting a parameter optimization request initiated by a target user for a parameter sampling algorithm; sending the parameter optimization request provided by the target user to a server, so that the server can determine a parameter sampling algorithm that matches the target user; Sending the sample acquisition request initiated by the target user to the server, so that the server responds to the sample acquisition request and calls the parameter sampling algorithm to generate a test sample; Determining a simulation result of the test sample based on a preset objective function; Outputting a simulation result of the test sample to the target user; after determining the simulation result of the test sample based on the preset objective function, the processing component is further configured to: obtain a judgment result of whether the test sample meets a preset convergence condition; if the judgment result is that the test sample meets the convergence condition, determining a target sample based on the test sample; If the judgment result is that the test sample does not meet the convergence condition, the process returns to sending the sample acquisition request initiated by the target user to the server, so that the server responds to the sample acquisition request and calls the parameter sampling algorithm to generate a test sample for continued execution.

Images